| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.17185821697099893, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008592910848549946, | |
| "eval_loss": 10.378536224365234, | |
| "eval_runtime": 2.4628, | |
| "eval_samples_per_second": 198.962, | |
| "eval_steps_per_second": 99.481, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004296455424274973, | |
| "grad_norm": 0.010985192842781544, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3786, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008592910848549946, | |
| "grad_norm": 0.010209411382675171, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3791, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01288936627282492, | |
| "grad_norm": 0.01133144460618496, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 10.3782, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.017185821697099892, | |
| "grad_norm": 0.011832349933683872, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 10.3785, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.021482277121374866, | |
| "grad_norm": 0.0108720101416111, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 10.3781, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02577873254564984, | |
| "grad_norm": 0.016251012682914734, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 10.3776, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03007518796992481, | |
| "grad_norm": 0.012109613977372646, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 10.3775, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.034371643394199784, | |
| "grad_norm": 0.015744652599096298, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 10.3769, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03866809881847476, | |
| "grad_norm": 0.013376533053815365, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 10.3772, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04296455424274973, | |
| "grad_norm": 0.02371077798306942, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 10.3756, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04296455424274973, | |
| "eval_loss": 10.37713623046875, | |
| "eval_runtime": 2.4659, | |
| "eval_samples_per_second": 198.71, | |
| "eval_steps_per_second": 99.355, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.047261009667024706, | |
| "grad_norm": 0.01536468043923378, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 10.3781, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.05155746509129968, | |
| "grad_norm": 0.015035259537398815, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 10.378, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.055853920515574654, | |
| "grad_norm": 0.017331380397081375, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 10.3773, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.06015037593984962, | |
| "grad_norm": 0.01693269982933998, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 10.3768, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0644468313641246, | |
| "grad_norm": 0.018788564950227737, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 10.3763, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.06874328678839957, | |
| "grad_norm": 0.01848599687218666, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 10.3765, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.07303974221267455, | |
| "grad_norm": 0.022367339581251144, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 10.3759, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.07733619763694952, | |
| "grad_norm": 0.026913169771432877, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 10.3743, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.08163265306122448, | |
| "grad_norm": 0.025651535019278526, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 10.3754, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.08592910848549946, | |
| "grad_norm": 0.035040900111198425, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 10.3744, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08592910848549946, | |
| "eval_loss": 10.375018119812012, | |
| "eval_runtime": 2.4717, | |
| "eval_samples_per_second": 198.245, | |
| "eval_steps_per_second": 99.123, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.09022556390977443, | |
| "grad_norm": 0.024812066927552223, | |
| "learning_rate": 5e-05, | |
| "loss": 10.375, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.09452201933404941, | |
| "grad_norm": 0.029139433056116104, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 10.375, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.09881847475832438, | |
| "grad_norm": 0.026183877140283585, | |
| "learning_rate": 4.17702704859633e-05, | |
| "loss": 10.3747, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.10311493018259936, | |
| "grad_norm": 0.028735578060150146, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 10.374, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.10741138560687433, | |
| "grad_norm": 0.02600599266588688, | |
| "learning_rate": 3.3765026539765834e-05, | |
| "loss": 10.3744, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.11170784103114931, | |
| "grad_norm": 0.037724222987890244, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 10.3742, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.11600429645542427, | |
| "grad_norm": 0.0350051075220108, | |
| "learning_rate": 2.6202630348146324e-05, | |
| "loss": 10.3731, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.12030075187969924, | |
| "grad_norm": 0.04115588963031769, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 10.3737, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.12459720730397422, | |
| "grad_norm": 0.034164655953645706, | |
| "learning_rate": 1.928936436551661e-05, | |
| "loss": 10.3718, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.1288936627282492, | |
| "grad_norm": 0.04169544205069542, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 10.3717, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.1288936627282492, | |
| "eval_loss": 10.373159408569336, | |
| "eval_runtime": 2.4689, | |
| "eval_samples_per_second": 198.468, | |
| "eval_steps_per_second": 99.234, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.13319011815252416, | |
| "grad_norm": 0.035568829625844955, | |
| "learning_rate": 1.3213804466343421e-05, | |
| "loss": 10.3739, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.13748657357679914, | |
| "grad_norm": 0.028946030884981155, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 10.3732, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.14178302900107412, | |
| "grad_norm": 0.029522452503442764, | |
| "learning_rate": 8.141676086873572e-06, | |
| "loss": 10.374, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.1460794844253491, | |
| "grad_norm": 0.03400672227144241, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 10.3731, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.15037593984962405, | |
| "grad_norm": 0.026614105328917503, | |
| "learning_rate": 4.2113336672471245e-06, | |
| "loss": 10.3742, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.15467239527389903, | |
| "grad_norm": 0.034079305827617645, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 10.3729, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.158968850698174, | |
| "grad_norm": 0.031550854444503784, | |
| "learning_rate": 1.5299867030334814e-06, | |
| "loss": 10.373, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.16326530612244897, | |
| "grad_norm": 0.03797019645571709, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 10.3725, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.16756176154672395, | |
| "grad_norm": 0.036687079817056656, | |
| "learning_rate": 1.7077534966650766e-07, | |
| "loss": 10.3732, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.17185821697099893, | |
| "grad_norm": 0.046533871442079544, | |
| "learning_rate": 0.0, | |
| "loss": 10.3721, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.17185821697099893, | |
| "eval_loss": 10.372811317443848, | |
| "eval_runtime": 2.4726, | |
| "eval_samples_per_second": 198.175, | |
| "eval_steps_per_second": 99.087, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 10124901089280.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |